spark SqlNetworkWordCount 源码

spark SqlNetworkWordCount 代码

文件路径：/examples/src/main/scala/org/apache/spark/examples/streaming/SqlNetworkWordCount.scala

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// scalastyle:off println
package org.apache.spark.examples.streaming

import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.{Seconds, StreamingContext, Time}

/**
 * Use DataFrames and SQL to count words in UTF8 encoded, '\n' delimited text received from the
 * network every second.
 *
 * Usage: SqlNetworkWordCount <hostname> <port>
 * <hostname> and <port> describe the TCP server that Spark Streaming would connect to receive data.
 *
 * To run this on your local machine, you need to first run a Netcat server
 *    `$ nc -lk 9999`
 * and then run the example
 *    `$ bin/run-example org.apache.spark.examples.streaming.SqlNetworkWordCount localhost 9999`
 */

object SqlNetworkWordCount {
  def main(args: Array[String]): Unit = {
    if (args.length < 2) {
      System.err.println("Usage: NetworkWordCount <hostname> <port>")
      System.exit(1)
    }

    StreamingExamples.setStreamingLogLevels()

    // Create the context with a 2 second batch size
    val sparkConf = new SparkConf().setAppName("SqlNetworkWordCount")
    val ssc = new StreamingContext(sparkConf, Seconds(2))

    // Create a socket stream on target ip:port and count the
    // words in input stream of \n delimited text (e.g. generated by 'nc')
    // Note that no duplication in storage level only for running locally.
    // Replication necessary in distributed scenario for fault tolerance.
    val lines = ssc.socketTextStream(args(0), args(1).toInt, StorageLevel.MEMORY_AND_DISK_SER)
    val words = lines.flatMap(_.split(" "))

    // Convert RDDs of the words DStream to DataFrame and run SQL query
    words.foreachRDD { (rdd: RDD[String], time: Time) =>
      // Get the singleton instance of SparkSession
      val spark = SparkSessionSingleton.getInstance(rdd.sparkContext.getConf)
      import spark.implicits._

      // Convert RDD[String] to RDD[case class] to DataFrame
      val wordsDataFrame = rdd.map(w => Record(w)).toDF()

      // Creates a temporary view using the DataFrame
      wordsDataFrame.createOrReplaceTempView("words")

      // Do word count on table using SQL and print it
      val wordCountsDataFrame =
        spark.sql("select word, count(*) as total from words group by word")
      println(s"========= $time =========")
      wordCountsDataFrame.show()
    }

    ssc.start()
    ssc.awaitTermination()
  }
}


/** Case class for converting RDD to DataFrame */
case class Record(word: String)


/** Lazily instantiated singleton instance of SparkSession */
object SparkSessionSingleton {

  @transient  private var instance: SparkSession = _

  def getInstance(sparkConf: SparkConf): SparkSession = {
    if (instance == null) {
      instance = SparkSession
        .builder
        .config(sparkConf)
        .getOrCreate()
    }
    instance
  }
}
// scalastyle:on println

相关信息

spark 源码目录

相关文章

spark CustomReceiver 源码

spark DirectKafkaWordCount 源码

spark DirectKerberizedKafkaWordCount 源码

spark HdfsWordCount 源码

spark NetworkWordCount 源码

spark QueueStream 源码

spark RawNetworkGrep 源码

spark RecoverableNetworkWordCount 源码

spark StatefulNetworkWordCount 源码

spark StreamingExamples 源码